@inproceedings{aldeneh-etal-2021-learning,
title = "Learning Paralinguistic Features from Audiobooks through Style Voice Conversion",
author = "Aldeneh, Zakaria and
Perez, Matthew and
Mower Provost, Emily",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.377/",
doi = "10.18653/v1/2021.naacl-main.377",
pages = "4736--4745",
abstract = "Paralinguistics, the non-lexical components of speech, play a crucial role in human-human interaction. Models designed to recognize paralinguistic information, particularly speech emotion and style, are difficult to train because of the limited labeled datasets available. In this work, we present a new framework that enables a neural network to learn to extract paralinguistic attributes from speech using data that are not annotated for emotion. We assess the utility of the learned embeddings on the downstream tasks of emotion recognition and speaking style detection, demonstrating significant improvements over surface acoustic features as well as over embeddings extracted from other unsupervised approaches. Our work enables future systems to leverage the learned embedding extractor as a separate component capable of highlighting the paralinguistic components of speech."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aldeneh-etal-2021-learning">
<titleInfo>
<title>Learning Paralinguistic Features from Audiobooks through Style Voice Conversion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zakaria</namePart>
<namePart type="family">Aldeneh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Perez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Mower Provost</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Paralinguistics, the non-lexical components of speech, play a crucial role in human-human interaction. Models designed to recognize paralinguistic information, particularly speech emotion and style, are difficult to train because of the limited labeled datasets available. In this work, we present a new framework that enables a neural network to learn to extract paralinguistic attributes from speech using data that are not annotated for emotion. We assess the utility of the learned embeddings on the downstream tasks of emotion recognition and speaking style detection, demonstrating significant improvements over surface acoustic features as well as over embeddings extracted from other unsupervised approaches. Our work enables future systems to leverage the learned embedding extractor as a separate component capable of highlighting the paralinguistic components of speech.</abstract>
<identifier type="citekey">aldeneh-etal-2021-learning</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.377</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.377/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>4736</start>
<end>4745</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Paralinguistic Features from Audiobooks through Style Voice Conversion
%A Aldeneh, Zakaria
%A Perez, Matthew
%A Mower Provost, Emily
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F aldeneh-etal-2021-learning
%X Paralinguistics, the non-lexical components of speech, play a crucial role in human-human interaction. Models designed to recognize paralinguistic information, particularly speech emotion and style, are difficult to train because of the limited labeled datasets available. In this work, we present a new framework that enables a neural network to learn to extract paralinguistic attributes from speech using data that are not annotated for emotion. We assess the utility of the learned embeddings on the downstream tasks of emotion recognition and speaking style detection, demonstrating significant improvements over surface acoustic features as well as over embeddings extracted from other unsupervised approaches. Our work enables future systems to leverage the learned embedding extractor as a separate component capable of highlighting the paralinguistic components of speech.
%R 10.18653/v1/2021.naacl-main.377
%U https://aclanthology.org/2021.naacl-main.377/
%U https://doi.org/10.18653/v1/2021.naacl-main.377
%P 4736-4745
Markdown (Informal)
[Learning Paralinguistic Features from Audiobooks through Style Voice Conversion](https://aclanthology.org/2021.naacl-main.377/) (Aldeneh et al., NAACL 2021)
ACL